Run 4. Outer Step 52. Inner Step 32.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576031,
-    5576032,
-    5576034,
-    5576037,
-    5576040,
-    5576042,
-    5576044
+    5576046,
+    5576050,
+    5576053,
+    5576055,
+    5576058
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 31,
+  "inner_step": 32,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:247a793d78e860335c1b46cc73314e4304eb3eeb016293a59f4bfb38595d747a
+oid sha256:fad25fdb07fccf2ef688a27645da7d56c8aa489847653f38458af73a2f49bd84
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:467efebee360a489010f99e01fde0eaa1b7caa5eb72e6482fab444e19a05bfb9
+oid sha256:0559ee39a0b3e6fb17ecaeba9c40e699db2323edf53ce7d83eaf9614b100b757
 size 4040701744